GPT-6 Astra

Comparator maximum available thinking/reasoning when reported, otherwise best available result; exact setting not identified by this grid. Argon self-computed in default ALE-Claw harness with a five-hour window and safety filters. Flagged responses return empty strings; episode may continue. Astra and Opus from the official board. Binary pass rate. Fable absent.

Provider-published launch claim, not independent measurement by Google for every row. Argon self-computed in default ALE-Claw harness with a five-hour window and safety filters. Flagged responses return empty strings; episode may continue. Astra and Opus from the official board. Binary pass rate. Fable absent. Methodology https://deepmind.google/models/evals-methodology/gemini-4-argon, SHA256 ff1df6bdeddc4c0f48840c09a8a7813b10ae7ad9e053892da68dabf64f09bff7. Preserve source rounding. Methodology says capabilities as of September 2026 and results as of October 2026; review date is source retrieval, not evaluation date.

Comparison limit: Provider-published claim. Independent source results are admitted separately with exact checkpoint, effort and compatible protocol; this grid does not establish a matched comparison.

Google Gemini 4 Argon launch and evaluation methodology · Launch grid row 15: Agent's Last Exam / GPT-6 Astra; methodology Additional Details · reviewed 2026-09-30

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Computer Use table / Agents' Last Exam / GPT‑6 Astra · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Abstract Reasoning table / ARC-AGI-1 / GPT‑6 Astra · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Abstract Reasoning table / ARC-AGI-2 / GPT‑6 Astra · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API; Responses API harness with two documented setting changes

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Abstract Reasoning table / ARC-AGI-3 / GPT‑6 Astra · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Coding table / Artificial Analysis Coding Agent Index v1.4 / GPT‑6 Astra · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / Artificial Analysis Intelligence Index v4.1.1 / GPT‑6 Astra · reviewed 2026-09-06

Comparator maximum available thinking/reasoning when reported, otherwise best available result; exact setting not identified by this grid. Private test set; results sourced from the official Zapier public leaderboard.

Provider-published launch claim, not independent measurement by Google for every row. Private test set; results sourced from the official Zapier public leaderboard. Methodology https://deepmind.google/models/evals-methodology/gemini-4-argon, SHA256 ff1df6bdeddc4c0f48840c09a8a7813b10ae7ad9e053892da68dabf64f09bff7. Preserve source rounding. Methodology says capabilities as of September 2026 and results as of October 2026; review date is source retrieval, not evaluation date.

Comparison limit: Provider-published claim. Independent source results are admitted separately with exact checkpoint, effort and compatible protocol; this grid does not establish a matched comparison.

Google Gemini 4 Argon launch and evaluation methodology · Launch grid row 2: AutomationBench / GPT-6 Astra; methodology Additional Details · reviewed 2026-09-30

Reported reasoning effort low. End-to-end business workflows using 47 tools across six business functions. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration.

Provider-published lab self-report. Published chart cost per task $1.08; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI.

Introducing GPT-6.1 Sol · Chart: AutomationBench / GPT-6 Astra / low · reviewed 2026-09-29

Reported reasoning effort medium. End-to-end business workflows using 47 tools across six business functions. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration.

Provider-published lab self-report. Published chart cost per task $1.27; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI.

Introducing GPT-6.1 Sol · Chart: AutomationBench / GPT-6 Astra / medium · reviewed 2026-09-29

Reported reasoning effort high. End-to-end business workflows using 47 tools across six business functions. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration.

Provider-published lab self-report. Published chart cost per task $1.44; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI.

Introducing GPT-6.1 Sol · Chart: AutomationBench / GPT-6 Astra / high · reviewed 2026-09-29

Reported reasoning effort xhigh. End-to-end business workflows using 47 tools across six business functions. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration.

Provider-published lab self-report. Published chart cost per task $1.5; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI.

Introducing GPT-6.1 Sol · Chart: AutomationBench / GPT-6 Astra / xhigh · reviewed 2026-09-29

Reported reasoning effort max. End-to-end business workflows using 47 tools across six business functions. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration.

Provider-published lab self-report. Published chart cost per task $1.73; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI.

Introducing GPT-6.1 Sol · Chart: AutomationBench / GPT-6 Astra / max · reviewed 2026-09-29

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / AutomationBench / GPT‑6 Astra · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API; tools enabled

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / BenchCAD / GPT‑6 Astra · reviewed 2026-09-06

Maximum reported across reasoning efforts; OpenAI research environment or API

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Professional table / BrowseComp / GPT‑6 Astra · reviewed 2026-09-06

Comparator maximum available thinking/reasoning when reported, otherwise best available result; exact setting not identified by this grid. Without tools; results from the official Surge public leaderboard.

Provider-published launch claim, not independent measurement by Google for every row. Without tools; results from the official Surge public leaderboard. Methodology https://deepmind.google/models/evals-methodology/gemini-4-argon, SHA256 ff1df6bdeddc4c0f48840c09a8a7813b10ae7ad9e053892da68dabf64f09bff7. Preserve source rounding. Methodology says capabilities as of September 2026 and results as of October 2026; review date is source retrieval, not evaluation date.

Comparison limit: Provider-published claim. Independent source results are admitted separately with exact checkpoint, effort and compatible protocol; this grid does not establish a matched comparison.

Google Gemini 4 Argon launch and evaluation methodology · Launch grid row 17: Chartography / GPT-6 Astra; methodology Additional Details · reviewed 2026-09-30

Reported reasoning effort xhigh. Unintended outcomes in deliberately adversarial computer- and browser-use workplace tasks; the updated harder safety subset, not OSWorld task success. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration.

Provider-published lab self-report. Safety stress outcomes are retained for inspection and excluded from capability scoring. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI.

Comparison limit: Safety failure behavior is not a capability or intelligence score.

Introducing GPT-6.1 Sol · Chart: Computer-use safety stress test (lower is better) / GPT-6 Astra / xhigh · reviewed 2026-09-29